Results 11 to 20 of about 12,314 (276)
A cluster-based resampling method for pseudo-relevance feedback
Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, 2008 Typical pseudo-relevance feedback methods assume the top-retrieved documents are relevant and use these pseudo-relevant documents to expand terms. The initial retrieval set can, however, contain a great deal of noise. In this paper, we present a cluster-based resampling method to select better pseudo-relevant documents based on the relevance model. The
Kyung-Soon Lee +2 more
openaire +3 more sources
QA4PRF: A Question Answering Based Framework for Pseudo Relevance Feedback
IEEE Access, 2021 Pseudo relevance feedback (PRF) automatically performs query expansion based on top-retrieved documents to better represent the user’s information need so as to improve the search results.
Handong Ma +8 more
doaj +1 more source
A Hybrid Text Generation-Based Query Expansion Method for Open-Domain Question Answering
Future Internet, 2023 In the two-stage open-domain question answering (OpenQA) systems, the retriever identifies a subset of relevant passages, which the reader then uses to extract or generate answers.
Wenhao Zhu +3 more
doaj +1 more source
Multitask Fine-Tuning for Passage Re-Ranking Using BM25 and Pseudo Relevance Feedback
IEEE Access, 2022 Passage re-ranking is a machine learning task that estimates relevance scores between a given query and candidate passages. Keyword features based on the lexical similarities between queries and passages have been traditionally used for the passage re ...
Meoungjun Kim, Youngjoong Ko
doaj +1 more source
Online Distillation for Pseudo-Relevance Feedback
CoRR, 2023 Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and documents. In this paper, we explore a departure from this offline distillation strategy by investigating whether a ...
Sean MacAvaney, Xi Wang 0012
openaire +2 more sources
Collaborative annotation for pseudo relevance feedback
, 2008 We present a pseudo relevance feedback technique for information retrieval, which expands keyword queries with semantic annotation found in the freely available Del.icio.us collaborative tagging system. We hypothesise that collaborative tags represent semantic information that may render queries more informative, and hence enhance retrieval performance.
Lioma, Christina +2 more
openaire +3 more sources
Positional relevance model for pseudo-relevance feedback [PDF]
Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval, 2010 Pseudo-relevance feedback is an effective technique for improving retrieval results. Traditional feedback algorithms use a whole feedback document as a unit to extract words for query expansion, which is not optimal as a document may cover several different topics and thus contain much irrelevant information.
Yuanhua Lv, ChengXiang Zhai
openaire +1 more source
Journal of Information Science Theory and Practice, 2021 Pseudo relevance feedback (PRF) is a powerful query expansion (QE) technique that prepares queries using the top k pseudo-relevant documents and choosing expansion elements.
Farhan Yasir Hadi +3 more
doaj +1 more source
Query expansion using the clustering of pseudo relevant documents with query sensitive similarity [PDF]
مجله مدل سازی در مهندسی, 2017 Query expansion as one of query adaptation approaches, improves retrieval effectiveness of information retrieval. Pseudo-relevance feedback (PRF) is a query expansion approach that supposes top-ranked documents are relevant to the query concept, and ...
Reza Khodaei +2 more
doaj +1 more source
Contrastive Refinement for Dense Retrieval Inference in the Open-Domain Question Answering Task
Future Internet, 2023 In recent years, dense retrieval has emerged as the primary method for open-domain question-answering (OpenQA). However, previous research often focused on the query side, neglecting the importance of the passage side.
Qiuhong Zhai +3 more
doaj +1 more source